Volume Tells: Dual Cycle-Consistent Diffusion for 3D Fluorescence Microscopy De-noising and Super-Resolution
Zelin Li, Chenwei Wang, Zhaoke Huang, Yiming Ma, Cunming Zhao, Zhongying Zhao, Hong Yan
摘要
3D fluorescence microscopy is essential for understanding fundamental life processes through long-term live-cell imaging. However, due to inherent issues in imaging principles, it faces significant challenges including spatially varying noise and anisotropic resolution, where the axial resolution lags behind the lateral resolution up to 4.5 times. Meanwhile, laser power is kept low to maintain cell viability, leading to inaccessible low-noise and high-resolution paired ground truth (GT). To tackle these limitations, a dual Cycle-consistent Diffusion is proposed to effectively mine intra-volume imaging priors within 3D cell volumes in an unsupervised manner, i.e., Volume Tells (VTCD), achieving de-noising and super-resolution (SR) simultaneously. Specifically, a spatially iso-distributed denoiser is designed to exploit the noise distribution consistency between adjacent low-noise and high-noise regions within the 3D cell volume, suppressing the spatially varying noise. Then, in light of the structural consistency of the cell volume, a cross-plane global-propagation SR module propagates high-resolution details from the XY plane into adjacent regions in the XZ and YZ planes, progressively enhancing resolution across the entire 3D cell volume. Experimental results on 10 in vivo cellular dataset demonstrate high improvements in both de-noising and super-resolution, with axial resolution enhanced from 430 nm to 90 nm.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- MicroFM: Physics-guided Flow Matching for Isotropic Microscopy ReconstructionXingzu Zhan, Runmin Jiang, Vatsal Gupta, Tanush Swaminathan 等CVPR 2026 · 被引用 1 次
- Recover Cell Tensor: Diffusion-Equivalent Tensor Completion for Fluorescence Microscopy ImagingChenwei Wang, Zhaoke Huang, Zelin Li, Wenqi ZhuICLR 2026
它引用的顶会 Paper16
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu 等ICCV 2021 · 被引用 31,683 次
- Cross Aggregation Transformer for Image RestorationZheng Chen, Yulun Zhang, Jinjin Gu, Yongbing Zhang 等NeurIPS 2022 · 被引用 274 次
- SinSR: Diffusion-Based Image Super-Resolution in a Single StepYufei Wang, Wenhan Yang, Xinyuan Chen, Yaohui Wang 等CVPR 2024 · 被引用 110 次
- Image Processing GNN: Breaking Rigidity in Super-ResolutionYuchuan Tian, Hanting Chen, Chao Xu, Yunhe WangCVPR 2024 · 被引用 34 次
相关 Paper
- V2V3D: View-to-View Denoised 3D Reconstruction for Light Field MicroscopyJiayin Zhao, Zhenqi Fu, Tao Yu, Hui QiaoCVPR 2025
- MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy ProjectionsMude Hui, Zihao Wei, Hongru Zhu, Fei Xia 等CVPR 2024
- Inverse Flow and Consistency ModelsYuchen Zhang, Jian ZhouICML 2025
- Recover Biological Structure from Sparse-View Diffraction Images with Neural Volumetric PriorRenzhi He, Haowen Zhou, Yubei Chen, Yi XueICCV 2025 · 被引用 1 次
- CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical DataWei Fang, Yuxing Tang, Heng Guo, Mingze Yuan 等CVPR 2024
